Audio-Text-to-Text
Transformers
Safetensors
midashenglm_spatial
text-generation
spatial-audio-understanding
multimodal
audio-language-model
audio
dasheng
custom_code
Instructions to use mispeech/midashenglm-spatial with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mispeech/midashenglm-spatial with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("mispeech/midashenglm-spatial", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from mispeech/midashenglm-spatial: direct link, hf CLI and curl.
- Browser
- Download file 362 Bytes
-
https://huggingface.co/mispeech/midashenglm-spatial/resolve/main/processor_config.json
- Command line
-
hf download hf://mispeech/midashenglm-spatial/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/mispeech/midashenglm-spatial/resolve/main/processor_config.json
362 Bytes
| { | |
| "audio_bos_token": "<|audio_bos|>", | |
| "audio_eos_token": "<|audio_eos|>", | |
| "audio_token": "<|AUDIO|>", | |
| "audio_channels": 2, | |
| "sem_n_fft": 512, | |
| "min_audio_duration": 0.2, | |
| "auto_map": { | |
| "AutoProcessor": "processing_midashenglm_spatial.MiDashengLMSpatialProcessor" | |
| }, | |
| "model_subsampling": 5, | |
| "processor_class": "MiDashengLMSpatialProcessor" | |
| } | |